Delete unused screenshots and update README.md and parse-readme.js

README.md

@@ -10,3 +10,5 @@
 | [Facebook](https://www.facebook.com)         | #socialmedia; #networking     |
 | [Amazon](https://www.amazon.com)             | #ecommerce; #retail           |
 | [Netflix](https://www.netflix.com)           | #streaming; #entertainment    |
+| [Spotify](https://www.spotify.com)           | #music; #streaming            |
+| [Microsoft](https://www.microsoft.com)       | #technology; #software        |

docs/data.json

@@ -1,10 +1,130 @@
 [
   {
-    "timestamp": "2024-03-09T22:57:11.586Z",
-    "firstName": "Ad42sw2am",
-    "lastName": "Alst4ws2on",
-    "githubProfile": "https://vuejs.org/",
-    "githubReadme": "https://vuejs.org/",
-    "screenshotPath": "screenshots/6s.jpeg"
+    "timestamp": "2024-03-14T20:17:31.711Z",
+    "title": "Accelerate the Development of AI Applications | Scale AI",
+    "url": "https://www.scale.ai",
+    "companyName": "Scale",
+    "screenshotPath": "screenshots/Scale.jpeg",
+    "tags": [
+      "startup"
+    ],
+    "stack": "React",
+    "timeToPageLoad": 439
+  },
+  {
+    "timestamp": "2024-03-14T20:17:33.325Z",
+    "title": "The #1 AI Headshot Generator for Professional Headshots",
+    "url": "https://www.headshotpro.com",
+    "companyName": "Head Shot Pro",
+    "screenshotPath": "screenshots/HeadShotPro.jpeg",
+    "tags": [
+      "startup"
+    ],
+    "stack": "Nuxt.js",
+    "timeToPageLoad": 41
+  },
+  {
+    "timestamp": "2024-03-14T20:17:34.118Z",
+    "title": "Airbnb | Vacation rentals, cabins, beach houses, & more",
+    "url": "https://www.airbnb.com",
+    "companyName": "Airbnb",
+    "screenshotPath": "screenshots/Airbnb.jpeg",
+    "tags": [
+      "travel",
+      "rental"
+    ],
+    "stack": "React",
+    "timeToPageLoad": 462
+  },
+  {
+    "timestamp": "2024-03-14T20:17:34.987Z",
+    "title": "Erziele Umsätze als Fahrer*in oder bestelle jetzt eine Fahrt | Uber Deutschland",
+    "url": "https://www.uber.com",
+    "companyName": "Uber",
+    "screenshotPath": "screenshots/Uber.jpeg",
+    "tags": [
+      "transportation",
+      "ridesharing"
+    ],
+    "stack": "",
+    "timeToPageLoad": 180
+  },
+  {
+    "timestamp": "2024-03-14T20:17:35.580Z",
+    "title": "Google",
+    "url": "https://www.google.com",
+    "companyName": "Google",
+    "screenshotPath": "screenshots/Google.jpeg",
+    "tags": [
+      "search",
+      "technology"
+    ],
+    "stack": "",
+    "timeToPageLoad": 180
+  },
+  {
+    "timestamp": "2024-03-14T20:17:36.056Z",
+    "title": "Facebook - log in or sign up",
+    "url": "https://www.facebook.com",
+    "companyName": "Facebook",
+    "screenshotPath": "screenshots/Facebook.jpeg",
+    "tags": [
+      "socialmedia",
+      "networking"
+    ],
+    "stack": "",
+    "timeToPageLoad": 144
+  },
+  {
+    "timestamp": "2024-03-14T20:17:37.278Z",
+    "title": "Amazon.com. Spend less. Smile more.",
+    "url": "https://www.amazon.com",
+    "companyName": "Amazon",
+    "screenshotPath": "screenshots/Amazon.jpeg",
+    "tags": [
+      "ecommerce",
+      "retail"
+    ],
+    "stack": "",
+    "timeToPageLoad": 510
+  },
+  {
+    "timestamp": "2024-03-14T20:17:38.943Z",
+    "title": "Netflix - Watch TV Shows Online, Watch Movies Online",
+    "url": "https://www.netflix.com",
+    "companyName": "Netflix",
+    "screenshotPath": "screenshots/Netflix.jpeg",
+    "tags": [
+      "streaming",
+      "entertainment"
+    ],
+    "stack": "React",
+    "timeToPageLoad": 595
+  },
+  {
+    "timestamp": "2024-03-14T20:17:40.770Z",
+    "title": "Spotify - Web Player: Music for everyone",
+    "url": "https://www.spotify.com",
+    "companyName": "Spotify",
+    "screenshotPath": "screenshots/Spotify.jpeg",
+    "tags": [
+      "music",
+      "streaming"
+    ],
+    "stack": "React",
+    "timeToPageLoad": 70
+  },
+  {
+    "timestamp": "2024-03-14T20:17:43.056Z",
+    "title": "Microsoft – Cloud, Computer, Apps und Gaming",
+    "url": "https://www.microsoft.com",
+    "companyName": "Microsoft",
+    "screenshotPath": "screenshots/Microsoft.jpeg",
+    "tags": [
+      "technology",
+      "software"
+    ],
+    "stack": "jQuery",
+    "timeToPageLoad": 1060
   }
 ]

docs/parse-readme.js

@@ -79,16 +79,35 @@ const getWebsiteStack = async (page) => {
 
         if (!!window.Nuxt || !!window.__NUXT__)
             return 'Nuxt.js';
+
+        return ''; 
     });
 }
 
+const updateDataFile = async (dataObjects) => {
+    const dataFilePath = path.join(__dirname, 'data.json');
+    let existingData;
+
+    try {
+        existingData = JSON.parse(await fs.readFile(dataFilePath, 'utf8'));
+    } catch (error) {
+        existingData = [];
+    }
+
+    const newData = dataObjects.filter(dataObject => 
+        !existingData.some(existingObject => existingObject.companyName === dataObject.companyName)
+    );
+
+    await fs.writeFile(dataFilePath, JSON.stringify([...existingData, ...newData], null, 2));
+}
 
 const processFile = async (filePath) => {
 
     data = await fs.readFile(filePath, 'utf8');
     const browser = await puppeteer.launch();
     const tableRowRegex = /\|\s*\[([^\]]+)\]\(([^)]+)\)\s*\|\s*([^|]+)\s*\|/g;
     let dataObjects = [];
+    let match;
 
     while ((match = tableRowRegex.exec(data)) !== null) {
 
@@ -108,19 +127,21 @@ const processFile = async (filePath) => {
 
         const dataObject = {
             timestamp: new Date().toISOString(),
-            title,
-            url,
-            companyName,
+            title: title,
+            url: url,
+            companyName: companyName,
             screenshotPath: `screenshots/${companyName.replace(/\s/g, '')}.jpeg`,
-            tags,
+            tags: tags,
             stack: websiteStack,
-            timeToPageLoad
+            timeToPageLoad: Math.round(timeToPageLoad),
         };
         console.log(dataObject);
         dataObjects.push(dataObject);
     }
     await browser.close(); 
 
+    await updateDataFile(dataObjects);
+
     //const json = JSON.stringify(dataObjects, null, 2);
     //console.log(json);
 }
@@ -137,16 +158,16 @@ fs.readFile(dataFilePath, 'utf8', (err, data) => {
         return;
     }
 
-    // Initialize an array to hold the existing users
-    let existingUsers = [];
+    // Initialize an array to hold the existing data objects
+    let existingDataObjects = [];
 
-    // If the file has data, parse it as JSON and assign it to existingUsers
+    // If the file has data, parse the data into an array
     if (data) {
-        existingUsers = JSON.parse(data);
+        existingDataObjects = JSON.parse(data);
     }
 
     // Filter out the users that already exist in the data file
-    const newUsers = users.filter(user => !existingUsers.some(existingUser => existingUser.githubProfile === user.githubProfile));
+    const newDataObjects = users.filter(user => !existingUsers.some(existingUser => existingUser.githubProfile === user.githubProfile));
 
     // Combine the existing users and the new users
     const allUsers = [...existingUsers, ...newUsers];
@@ -165,5 +186,5 @@ fs.readFile(dataFilePath, 'utf8', (err, data) => {
         // Log a success message
         console.log('Data written to file');
     });
-}); */
-//});
+});
+*/

docs/screenshot.js

@@ -0,0 +1,48 @@
+const puppeteer = require('puppeteer');
+const fs = require('fs');
+const path = require('path');
+
+(async () => {
+    const data = JSON.parse(fs.readFileSync('docs/data.json', 'utf-8'));
+    const browser = await puppeteer.launch();
+
+    for (const dataObject of data) {
+        const screenshotPath = path.join('docs', dataObject.screenshotPath);
+        if (fs.existsSync(screenshotPath)) {
+            console.log(`Screenshot already exists for ${dataObject.companyName}, skipping.`);
+            continue;
+        }
+
+        console.log(`Taking screenshot for ${dataObject.companyName} ...`);
+
+        const page = await browser.newPage();
+        await page.setViewport({ width: 1280, height: 720 });
+        await page.goto(dataObject.url);
+        await new Promise(resolve => setTimeout(resolve, 3000));
+
+         // Scroll to the bottom of the page
+         await page.evaluate(async () => {
+            await new Promise((resolve, reject) => {
+                var totalHeight = 0;
+                var distance = 100;
+                var timer = setInterval(() => {
+                    var scrollHeight = document.body.scrollHeight;
+                    window.scrollBy(0, distance);
+                    totalHeight += distance;
+
+                    if (totalHeight >= scrollHeight){
+                        clearInterval(timer);
+                        resolve();
+                    }
+                }, 100);
+            });
+        });
+
+
+
+        await page.screenshot({ path: screenshotPath, fullPage: true });
+        await page.close();
+    }
+
+    await browser.close();
+})();